视觉大模型 / VLM - arXivDaily 专题

2502.19958 2025-06-03 cs.CV 79%

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

Ke Niu, Haiyang Yu, Mengyang Zhao, Teng Fu, Siyang Yi, Wei Lu, Bin Li, Xuelin Qian, Xiangyang Xue

机构 * Fudan University（复旦大学）； Northwestern Polytechnical University（西北工业大学）

专题命中视觉推理：vision language model(title)；vision-language model(abstract)；分类 cs.CV

2505.24476 2025-06-02 cs.CV 79%

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

Yuting Zhang, Hao Lu, Qingyong Hu, Yin Wang, Kaishen Yuan, Xin Liu, Kaishun Wu

机构 * The Hong Kong University of Science & Technology (Guangzhou)（香港科技大学（广州））； The Hong Kong University of Science & Technology（香港科技大学）； Zhejiang University（浙江大学）； Lappeenranta-Lahti University of Technology（拉佩兰塔-拉赫蒂技术大学）

专题命中视觉推理：multimodal large language model(title,abstract)；分类 cs.CV

Comments Accepted by CVPR 2025

2505.21374 2025-05-28 cs.CV 79%

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

Junhao Cheng, Yuying Ge, Teng Wang, Yixiao Ge, Jing Liao, Ying Shan

机构 * ARC Lab, Tencent PCG（腾讯PCG广告实验室）； City University of Hong Kong（香港城市大学）

专题命中视觉推理：MLLM(title)；grounding(abstract)；分类 cs.CV

Comments Homepage: https://github.com/TencentARC/Video-Holmes

2505.16517 2025-05-27 cs.RO cs.CV 79%

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models

Zirui Song, Guangxian Ouyang, Mingzhe Li, Yuheng Ji, Chenxi Wang, Zixiang Xu, Zeyu Zhang, Xiaoqing Zhang, Qian Jiang, Zhenhao Chen, Zhongzhi Li, Rui Yan, Xiuying Chen

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫扎伊德·本·扎耶德人工智能大学）； ByteDance（字节跳动）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； The Australia National University（澳大利亚国立大学）； Renmin University of China（中国人民大学）； Wuhan University（武汉大学）

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments 14pages

2410.00193 2025-05-27 cs.CL cs.CV 79%

Do Vision-Language Models Really Understand Visual Language?

Yifan Hou, Buse Giledereli, Yilei Tu, Mrinmaya Sachan

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments ICML 2025

2505.16446 2025-05-23 cs.LG 79%

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models

Zhaoxin Wang, Handing Wang, Cong Tian, Yaochu Jin

机构 * Xidian University（西安电子科技大学）； Westlake University（西湖大学）

专题命中视觉推理：vision-language model(title)；multimodal large language model(abstract)；分类 cs.LG

2410.05096 2025-05-23 cs.CV 79%

Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llava

Mehdi Azarafza, Fatima Idrees, Ali Ehteshami Bejnordi, Charles Steinmetz, Stefan Henkler, Achim Rettberg

机构 * Department of Computer Science Univ. of Applied Science Hamm-Lippstadt（计算机科学系应用科学大学哈姆-利普施塔特）； Carl von Ossietzky University of Oldenburg（卡尔·冯·奥西埃茨基旧恩堡大学）

专题命中视觉推理：LLaVA(title,abstract)；分类 cs.CV

Comments 10 pages, 6 figures

2505.15154 2025-05-22 cs.CL cs.AI cs.MM 79%

Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning

Jinghui Lu, Haiyang Yu, Siliang Xu, Shiwei Ran, Guozhi Tang, Siqi Wang, Bin Shan, Teng Fu, Hao Feng, Jingqun Tang, Han Wang, Can Huang

机构 * ByteDance（字节跳动）； FuDan University（复旦大学）

专题命中视觉推理：MLLM(title)；multimodal large language model(abstract)；分类 cs.AI

2505.12000 2025-05-20 cs.CV 79%

IQBench: How "Smart'' Are Vision-Language Models? A Study with Human IQ Tests

Tan-Hanh Pham, Phu-Vinh Nguyen, Dang The Hung, Bui Trong Duong, Vu Nguyen Thanh, Chris Ngo, Tri Quang Truong, Truong-Son Hy

机构 * Harvard Medical School（哈佛医学院）； Uppsala University（乌普萨拉大学）； University of London（伦敦大学）； Vietnam Military Medical University（越南军医大学）； University of Technical Education Ho Chi Minh City（胡志明市技术大学）； Knovel Engineering Lab（Knovel工程实验室）； University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments IQ Test for Multimodal Models

2403.16184 2025-04-30 cs.CV 79%

Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement

Yuxuan Wang, Xiaoyuan Liu

机构 * Nanyang Technological University（南洋理工大学）

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

2503.12542 2025-04-24 cs.CV 79%

ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos

Peiran Wu, Yunze Liu, Miao Liu, Junxiao Shen

机构 * University of Bristol（布里斯托大学）； X-Intelligence Labs（X-智能实验室）； Meta

专题命中视觉推理：multimodal large language model(title,abstract)；分类 cs.CV

2411.18203 2025-04-24 cs.CV cs.CL 79%

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

Di Zhang, Junxian Li, Jingdi Lei, Xunzhi Wang, Yujie Liu, Zonglin Yang, Jiatong Li, Weida Wang, Suorong Yang, Jianbo Wu, Peng Ye, Wanli Ouyang, Dongzhan Zhou

机构 * Fudan University（复旦大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Shanghai Jiaotong University（上海交通大学）； Nankai University（南开大学）； Shanghai University（上海大学）； Nanyang Technological University（南洋理工大学）； Hong Kong Polytechnic University（香港理工大学）； Tongji University（同济大学）； Nanjing University（南京大学）； University of California, Merced（加州大学梅德福分校）； Chinese University of Hong Kong（香港中文大学）

专题命中视觉推理：VLM(title)；vision-language model(abstract)；分类 cs.CV

Comments 16 pages, 11 figures

2504.07521 2025-04-18 cs.AI cs.MM 79%

Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models

Yuxiang Lin, Jingdong Sun, Zhi-Qi Cheng, Jue Wang, Haomin Liang, Zebang Cheng, Yifei Dong, Jun-Yan He, Xiaojiang Peng, Xian-Sheng Hua

专题命中视觉推理：multimodal large language model(title)；vision-language model(abstract)；分类 cs.AI

Comments Accepted at CVPR Workshop NEXD 2025. 21 pages, Project: https://github.com/Lum1104/EIBench

2410.17385 2025-04-18 cs.CL cs.CV 79%

Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities

Zheyuan Zhang, Fengyuan Hu, Jayjun Lee, Freda Shi, Parisa Kordjamshidi, Joyce Chai, Ziqiao Ma

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments Accepted to ICLR 2025 (Oral) | Project page: https://spatial-comfort.github.io/

2504.09979 2025-04-15 cs.CV 79%

Resampling Benchmark for Efficient Comprehensive Evaluation of Large Vision-Language Models

Teppei Suzuki, Keisuke Ozawa

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

2504.08111 2025-04-14 cs.CV 79%

POEM: Precise Object-level Editing via MLLM control

Marco Schouten, Mehmet Onurcan Kaya, Serge Belongie, Dim P. Papadopoulos

专题命中视觉推理：MLLM(title)；multimodal large language model(abstract)；分类 cs.CV

Comments Accepted to SCIA 2025

2503.13947 2025-04-14 cs.CV 79%

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

Sayak Nag, Udita Ghosh, Calvin-Khang Ta, Sarosij Bose, Jiachen Li, Amit K Roy Chowdhury

专题命中视觉推理：MLLM(title,abstract)；分类 cs.CV

Comments Accepted at CVPR 2025

2411.10442 2025-04-08 cs.CL cs.CV 79%

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

Weiyun Wang, Zhe Chen, Wenhai Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Jinguo Zhu, Xizhou Zhu, Lewei Lu, Yu Qiao, Jifeng Dai

专题命中视觉推理：multimodal large language model(title,abstract)；分类 cs.CV

2503.23064 2025-04-03 cs.CV 79%

VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models

Yufan Ren, Konstantinos Tertikas, Shalini Maiti, Junlin Han, Tong Zhang, Sabine Süsstrunk, Filippos Kokkinos

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments 8 pages; Project page: https://yufan-ren.com/subpage/VGRP-Bench/

2411.13543 2025-04-02 cs.AI 79%

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Davide Paglieri, Bartłomiej Cupiał, Samuel Coward, Ulyana Piterbarg, Maciej Wolczyk, Akbir Khan, Eduardo Pignatelli, Łukasz Kuciński, Lerrel Pinto, Rob Fergus, Jakob Nicolaus Foerster, Jack Parker-Holder, Tim Rocktäschel

专题命中视觉推理：VLM(title)；vision language model(abstract)；分类 cs.AI

Comments Published as a conference paper at ICLR 2025

2409.20213 2025-04-02 cs.CV 79%

Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning

Oleh Kolner, Thomas Ortner, Stanisław Woźniak, Angeliki Pantazi

专题命中视觉推理：visual reasoning(title,abstract)；分类 cs.CV

Comments 10 pages of main text and 8 pages appendices

Journal ref The Thirteenth International Conference on Learning Representations (ICLR) 2025

2503.12496 2025-03-31 cs.CV 79%

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

Tianyuan Qu, Longxiang Tang, Bohao Peng, Senqiao Yang, Bei Yu, Jiaya Jia

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

2412.08614 2025-03-27 cs.CV 79%

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

Fan Lu, Wei Wu, Kecheng Zheng, Shuailei Ma, Biao Gong, Jiawei Liu, Wei Zhai, Yang Cao, Yujun Shen, Zheng-Jun Zha

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments Accepted by CVPR2025. Code and Dataset: https://github.com/LuFan31/CompreCap

2503.18533 2025-03-25 cs.AI 79%

MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning

Dawei Yan, Yang Li, Qing-Guo Chen, Weihua Luo, Peng Wang, Haokui Zhang, Chunhua Shen

专题命中视觉推理：visual language model(title)；vision-language model(abstract)；分类 cs.AI

2503.14161 2025-03-19 cs.CV 79%

CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models

Yiqi Zhu, Ziyue Wang, Can Zhang, Peng Li, Yang Liu

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

2503.13440 2025-03-19 cs.CV 79%

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling

Yingyue Li, Bencheng Liao, Wenyu Liu, Xinggang Wang

专题命中视觉推理：vision-language model(title)；VLM(abstract)；分类 cs.CV

Comments Code and model are available at http://github.com/hustvl/MaTVLM

2502.07601 2025-03-18 cs.CV cs.CL 79%

Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models

Jiacong Xu, Shao-Yuan Lo, Bardia Safaei, Vishal M. Patel, Isht Dwivedi

专题命中视觉推理：multimodal large language model(title,abstract)；分类 cs.CV

Comments 19 pages, 10 figures, accepted by CVPR 2025

2501.11347 2025-03-18 cs.CV 79%

EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery

Guankun Wang, Long Bai, Junyi Wang, Kun Yuan, Zhen Li, Tianxu Jiang, Xiting He, Jinlin Wu, Zhen Chen, Zhen Lei, Hongbin Liu, Jiazheng Wang, Fan Zhang, Nicolas Padoy, Nassir Navab, Hongliang Ren

专题命中视觉推理：multimodal large language model(title,abstract)；分类 cs.CV

2503.11342 2025-03-17 cs.CV 79%

Road Rage Reasoning with Vision-language Models (VLMs): Task Definition and Evaluation Dataset

Yibing Weng, Yu Gu, Fuji Ren

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

2403.20312 2025-03-13 cs.CV 79%

Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations

Jaisidh Singh, Ishaan Shrivastava, Mayank Vatsa, Richa Singh, Aparna Bharati

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments 14 pages + 6 figures in main manuscript (excluding references)

Journal ref WACV 2025 pages(7991-8001)

1. 视觉推理 4507 篇

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models

Do Vision-Language Models Really Understand Visual Language?

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models

Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llava

Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning

IQBench: How "Smart'' Are Vision-Language Models? A Study with Human IQ Tests

Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement

ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models

Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities

Resampling Benchmark for Efficient Comprehensive Evaluation of Large Vision-Language Models

POEM: Precise Object-level Editing via MLLM control

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning

CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling

Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models

EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery

Road Rage Reasoning with Vision-language Models (VLMs): Task Definition and Evaluation Dataset

Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations